<![CDATA[Additive Manufacturing (AM), particularly Laser Powder Bed Fusion (L-PBF), has become increasingly important for producing components in critical industries such as aerospace, automotive, and medical devices. However, predicting the failure risk of these components, especially due to fatigue, remains a challenge due to the variability in material properties and process-induced defects such as porosity. This research aims to develop a predictive model to assess the failure risk of components produced through Additive Manufacturing, with a focus on integrating mechanical testing data and Finite Element Analysis (FEA) simulations to predict the fatigue life and the associated risk of failure. The study utilizes an experimental-computational approach, incorporating mechanical testing for tensile strength, fatigue testing, and microstructural analysis to gather data on material properties and defects. These data are then combined with FEA simulations to create a predictive model using multiple regression analysis. The model's accuracy is validated through k-fold cross-validation (k=5), with performance metrics including R² and RMSE. The results demonstrate that the model successfully predicts the failure risk of AM components, with R² values near 0.95 and RMSE values indicating high accuracy in predicting fatigue life. The model also highlights the significant influence of porosity and stress concentration on fatigue failure, providing valuable insights into the optimization of AM process parameters to improve component durability.]]>
Copyrights © 2026
